The field of music generation and analysis is rapidly advancing, with a focus on developing more sophisticated and biologically plausible models. Recent work has emphasized the importance of comprehensive evaluation frameworks, incorporating both objective metrics and human perceptual judgment to assess musical quality. The use of spiking neural networks, transformers, and other innovative architectures is becoming increasingly prevalent, enabling more accurate and efficient music generation and analysis. Noteworthy papers include MuSpike, which introduces a unified benchmark and evaluation framework for symbolic music generation with spiking neural networks, and Amadeus, which proposes a novel autoregressive model with bidirectional attribute modelling for symbolic music generation. MQAD is also notable, as it presents a large-scale question answering dataset for training music large language models, enabling exploration into the inherent structure of music within a song.